Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    reference to comments sections in articles or posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.74
    agall
    -0.62
    roots
    -0.61
    glers
    -0.61
    Definition
    -0.60
    ISM
    -0.60
     DUI
    -0.60
    ISH
    -0.59
    isen
    -0.59
    nostic
    -0.58
    POSITIVE LOGITS
     below
    1.05
     section
    0.98
    below
    0.87
     sections
    0.87
     comments
    0.85
     forums
    0.81
     sidebar
    0.81
    pring
    0.79
     pane
    0.79
    ariat
    0.78
    Act Density 0.015%

    No Known Activations